Search

Many successful learning algorithms have been recently developed to represent graph-structured data. For example, Graph Neural Networks (GNNs) have achieved considerable successes in various tasks such as node classification, graph classification, and link prediction. However, these methods are highly dependent on the quality of the input graph structure. One used approach to alleviate this problem is to learn the graph structure instead of relying on a manually designed graph. In this paper, we introduce a new graph structure learning approach using multi-view learning, named MV-GSL (Multi-View Graph Structure Learning), in which we aggregate different graph structure learning methods using subspace merging on Grassmann manifold to improve the quality of the learned graph structures. Extensive experiments are performed to evaluate the effectiveness of the proposed method on two benchmark datasets, Cora and Citeseer. Our experiments show that the proposed method has promising performance compared to single and other combined graph structure learning methods. [ABSTRACT FROM AUTHOR]

Nowadays, individuals spend significant time on online social networks and microblogging websites, consuming news and expressing their opinions and viewpoints on various topics. It is an excellent source of data for various data mining applications, such as sentiment analysis. Mining this type of data presents several challenges, including the posts' short length and informal language. On the other hand, microblog posts contain a high degree of interdependence, which can help to improve sentiment classification based on text. This data can be represented as a graph, with nodes representing posts and edges representing the various relationships between them. By using recently developed deep learning models for graph structures, this approach enables efficient sentiment analysis of microblog posts. This paper utilizes graphs to represent microblog posts and their various relationships, such as user, friendship, hashtag, sentimental similarity, textual similarity, and common friends. It then employs graph neural networks to perform context-aware sentiment analysis. To make use of the knowledge contained in multiple graphs, we propose a stacking model that simultaneously employs multiple graph types. The findings demonstrate the relevance of sociological theories to the analysis of social media. Experimental results on HCR (a real-world Twitter sentiment analysis dataset), indicate that the proposed approach outperforms baselines and state-of-the-art models. [ABSTRACT FROM AUTHOR]

Fake news detection is a challenging problem in online social media, with considerable social and political impacts. Several methods have already been proposed for the automatic detection of fake news, which are often based on the statistical features of the content or context of news. In this paper, we propose a novel fake news detection method based on Natural Language Inference (NLI) approach. Instead of using only statistical features of the content or context of the news, the proposed method exploits a human-like approach, which is based on inferring veracity using a set of reliable news. In this method, the related and similar news published in reputable news sources are used as auxiliary knowledge to infer the veracity of a given news item. We also collect and publish the first inference-based fake news detection dataset, called FNID, in two formats: the two-class version (FNID-FakeNewsNet) and the six-class version (FNID-LIAR). We use the NLI approach to boost several classical and deep machine learning models, including Decision Tree, Naïve Bayes, Random Forest, Logistic Regression, k-Nearest Neighbors, Support Vector Machine, BiGRU, and BiLSTM along with different word embedding methods including Word2vec, GloVe, fastText, and BERT. The experiments show that the proposed method achieves 85.58% and 41.31% accuracies in the FNID-FakeNewsNet and FNID-LIAR datasets, respectively, which are 10.44% and 13.19% respective absolute improvements. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new method for detecting adversarial attacks on deep neural networks. Our algorithm is based on the intuition that attacking input images results in different displacement vectors for clean and adversarial classes. For example, if the input image is an adversarial example, the re-attacking process results in a displacement vector with a short length in the feature space, but this displacement is considerable for clean images. We train our detector based on these displacement vectors. The experimental results show that compared to the current learning-based adversarial detection methods, the proposed system is capable of detecting the adversarial examples using a far simpler network. In addition, the proposed method is independent of the attack type, and is able to detect even novel attacks. It is also revealed that the proposed system learns the discrimination function even using a small amount of training data without any hyper-parameter tuning. We obtain remarkable results in detecting adversarial examples which are placed near and far from the decision boundary, improving state-of-the-art in detecting 2-norm Carlini and Wagner attack (L2-C&W) and ∞-norm Projected Gradient Descent attack (L∞-PGD), where just Fast Gradient Sign Method (FGSM) is used for training the system. [ABSTRACT FROM AUTHOR]

In this paper, a novel approach is presented to identify the smart home residents. The different behavioral patterns of smart home's inhabitants are exploited to distinguish the residents. The variation of a specific individual behavior in smart homes is a significant challenge. We introduce different features that are useful to handle this problem. Moreover, we introduce an innovative strategy which considers the Bag of Sensor Events and Bayesian networks. In the Bag of Sensor Events approach, the frequency of each sensor event occurrence is considered, regardless of the order of sensor events. The efficiency of the Bag of sensor Events approach is compared to the Sequence of Sensor Events. Our experiments confirm that the Bag of Sensor Events approach outperformed the previous approaches. When the smart homes residents are people who repeat their daily activities frequently, applying the Bag of Sensor Events on Activity Based Window Frame features, which considers the performed daily activities, would identify them more accurately. In contrast, in cases where residents perform their activities in different ways, considering the Time Based Window Frame leads to higher accuracy in distinguishing residents. In this approach, the features are created by considering the constant time intervals. The F-measure of our proposed approach on the Twor2009, Tulum2009, and Tulum2010 datasets is 96%, 100%, and 99%, respectively, which improves the results of the previous researches which consider behavioral patterns to identify smart home residents. [ABSTRACT FROM AUTHOR]

In many supervised learning problems, determining the true labels of training instances is expensive, laborious, and even practically impossible. As an alternative approach, it is much easier to collect multiple subjective (possibly noisy) labels from human labelers, especially with the crowdsourcing services such as Amazon's Mechanical Turk. The collected labels are then aggregated to estimate the true labels. In order to reduce the negative effects of novices, spammers, and malicious labelers, it necessitates taking into account the accuracies of the labelers. However, in the absence of true labels, we miss the main source of information to estimate the labeler accuracies. This paper demonstrates that the agreements or disagreements among labeler opinions are useful sources of information and facilitate the accuracy estimation problem. We represent this estimation problem as an optimization problem which its goal is to minimize the differences between the analytical probabilities of disagreements based on estimated accuracies and the probabilities of disagreements according to the provided labels. We present an efficient semi-exhaustive search method to solve this optimization problem. Our experiments on the simulated data and three real datasets show that the proposed method is a promising idea in this emerging new area. The source code of the proposed method is available for downloading at . [ABSTRACT FROM AUTHOR]